KR20220129913A - System for providing stock trading service using pattern analysis - Google Patents

Abstract

Provided is a stock trading service provision system using pattern analysis, which comprises: an investor terminal which receives the time to sell or buy in response to at least one type of preset pattern, or sells or buys the number of stocks corresponding to a preset amount at the time of sell or buy when automatic trading is set; and a stock trading service providing server. The stock trading service providing server includes: a setting unit which defines and stores the shape of a graph in a comprehensive stock chart as at least one type of pattern; a mapping unit for mapping and storing the time to sell or buy in response to the at least one type of pattern; and a trading unit which transmits the time to sell or buy to the investor terminal, or sells or buys the number of stocks corresponding to the preset amount in the investor terminal at the time to sell or buy when the automatic trading is set. The present invention can inform the timing of stock trading.

Description

Stock trading service providing system using pattern analysis {SYSTEM FOR PROVIDING STOCK TRADING SERVICE USING PATTERN ANALYSIS}

The present invention relates to a stock trading service providing system using pattern analysis, and provides a platform for analyzing a chart to extract a time to sell or buy stocks, and to buy and sell stocks.

Since the beginning of securities trading, millions of people have made great strides to get excess returns in the market, but scholars have sharply argued that stock prices are predictable and unpredictable. Contrary to the efficient market hypothesis, there are still investors in the market who achieve superior investment performance through fundamental and technical analysis. Basic analysis consists of environmental analysis such as economic analysis, industry analysis, company analysis, etc. and financial analysis that looks at the financial condition, and it is a method to find and invest in stocks with a stock price lower than the intrinsic value of the company, whereas technical analysis tries to find everything in the chart . Because it is easier to access than fundamental analysis, most people who invest in stocks are more interested in technical analysis. The method of technical analysis can also be divided into several branches. The most representative are analysis of technical indicators such as price indicators, trend indicators, trading volume indicators, and market indicators, and pattern analysis, which predicts trends by analyzing the graph shape of charts.

At this time, a platform that provides information by analyzing charts and patterns has been researched and developed. In the issue (published on April 14, 2015), a pair of stocks has a similarity in movement patterns, is derived based on stock price normalization and stock price time axis fluctuation, and the type of movement pattern has similarity on the same time axis. In order to trade stocks using the W-chart, which is a fluctuation trend chart, a configuration for displaying ranking information of a precedence and trailing relationship type, which is a case in which there is a similarity on the time axis where there is a time difference between the companion relationship type or stock items, Using the closing price as the starting point, the stock price trend of the day is displayed as candles in the form of a beacon in the rising section and in the shape of a negative candle in the falling section, but only the highest and lowest prices are displayed as one candle without displaying the opening and closing prices of the day. Search stock items for the stock item, create a trend chart for the searched stock item, calculate the number of distributions of positive and negative peaks included within one or more preset upper and lower reference points for candles, and change trend charts and calculation results Each configuration for displaying on the screen is disclosed.

However, in recent years, there have been many cases of studying stock price patterns using various machine learning techniques including neural networks in the field of artificial intelligence. Short-term predictive power of price has increased when trying to capture the timing of trading through stock price prediction, but long-term predictive power is limited. In addition, there are studies that focus on how accurately a pattern is found, but whether or not the found pattern is suitable for trading is a separate issue, so it may be weak in practical terms. Although there are reports of the simplicity of classifying all patterns into turning points called previous highs and previous lows, and the finding of price predictive power in specific patterns, there have been no reports of performance utilized in the actual market. Accordingly, research and development of a platform that analyzes charts and patterns is required so that stock trading can be performed when a section corresponding to a preset pattern occurs.

In one embodiment of the present invention, when stocks that soared by more than a preset 1 percent on the day and the conditions that reached the upper limit of the previous day are met, Zone F is formed when the stock falls by more than a preset second percent compared to the mid-day high, and the share price is When the stock price rebounds when approaching or contacting the F zone, the F zone is formed. If the F zone is divided into 3 parts and does not go down each zone, a profit is generated. This is reformed, and the K-zone is defined as the one that shows a trend of rising again when the share price is touched, and the point when the stock price falls and touches or stays in the F and K zones is set as a buying point. It is possible to provide a method of providing a stock trading service using pattern analysis, which can inform the timing of stock trading. However, the technical task to be achieved by the present embodiment is not limited to the above-described technical task, and other technical tasks may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention receives a selling or buying time in response to at least one type of preset pattern, or at the selling or buying time when automatic trading is set. An investor terminal that sells or buys stocks in a quantity corresponding to a preset amount, a setting unit that defines and stores the graph shape in the stock chart as at least one type of pattern, and sells or buys in response to at least one type of pattern A mapping unit that maps and stores the time point, transmits the time of purchase or purchase to the investor terminal, or sells or buys the amount of stock corresponding to the amount set in the investor terminal at the time of sale or purchase when automatic trading is set and a stock trading service providing server including wealth.

According to any one of the above-described problem solving means of the present invention, when the stocks that surged by more than a preset 1% on the day and the conditions that reached the upper limit of the previous day are met and fall by more than a preset second percentage compared to the mid-day high, Zone F is formed When the stock price rebounds when the stock price approaches or comes into contact with the F zone, the F zone is formed. After dividing the F zone by 3, if the stock price does not go downwards in each zone, a profit is generated, and the stock price of the stock price When the stock price falls again, the zone is reformed, and when the share price is touched in the zone, the K-zone is defined as the trend that the stock price rises again. By setting , as a buying point, it is possible to inform the timing of stock trading.

1 is a view for explaining a stock trading service providing system using pattern analysis according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a stock trading service providing server included in the system of FIG. 1 .
3 and 4 are diagrams for explaining an embodiment in which a stock trading service using pattern analysis according to an embodiment of the present invention is implemented.
5 is an operation flowchart illustrating a method of providing a stock trading service using pattern analysis according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "electrically connected" with another element interposed therebetween. . Also, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated, and one or more other features However, it is to be understood that the existence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded in advance.

The terms "about," "substantially," and the like, to the extent used throughout the specification are used in or close to the numerical values when manufacturing and material tolerances inherent in the stated meaning are presented, and are intended to enhance the understanding of the present invention. To help, precise or absolute figures are used to prevent unfair use by unscrupulous infringers of the stated disclosure. As used throughout the specification of the present invention, the term "step of (to)" or "step of" does not mean "step for".

In this specification, a "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. In addition, one unit may be implemented using two or more hardware, and two or more units may be implemented by one hardware. Meanwhile, '~ unit' is not limited to software or hardware, and '~ unit' may be configured to be in an addressable storage medium or may be configured to reproduce one or more processors. Thus, as an example, '~' denotes components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. The functions provided in the components and '~ units' may be combined into a smaller number of components and '~ units' or further separated into additional components and '~ units'. In addition, components and '~ units' may be implemented to play one or more CPUs in a device or secure multimedia card.

In this specification, some of the operations or functions described as being performed by the terminal, apparatus, or device may be performed instead of in a server connected to the terminal, apparatus, or device. Similarly, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal means mapping or matching the terminal's unique number or personal identification information, which is the identification data of the terminal. can be interpreted as

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a view for explaining a stock trading service providing system using pattern analysis according to an embodiment of the present invention. Referring to FIG. 1 , the stock trading service providing system 1 using pattern analysis may include at least one investor terminal 100 , a stock trading service providing server 300 , and at least one information providing server 400 . can However, since the stock trading service providing system 1 using the pattern analysis of FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1 .

At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1 , at least one investor terminal 100 may be connected to the stock trading service providing server 300 through the network 200 . In addition, the stock trading service providing server 300 may be connected to at least one investor terminal 100 and at least one information providing server 400 through the network 200 . In addition, the at least one information providing server 400 may be connected to the stock trading service providing server 300 through the network 200 .

Here, the network refers to a connection structure in which information exchange is possible between each node, such as a plurality of terminals and servers, and an example of such a network includes a local area network (LAN), a wide area network (WAN: Wide Area Network), the Internet (WWW: World Wide Web), wired and wireless data communication networks, telephone networks, wired and wireless television networks, and the like. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), Wi-Fi (Wi-Fi) , Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth (Bluetooth) network, NFC ( Near-Field Communication) networks, satellite broadcast networks, analog broadcast networks, Digital Multimedia Broadcasting (DMB) networks, and the like are included, but are not limited thereto.

In the following, the term at least one is defined as a term including the singular and the plural, and even if at least one term does not exist, each component may exist in the singular or plural, and may mean the singular or plural. it will be self-evident In addition, that each component is provided in singular or plural may be changed according to embodiments.

The at least one investor terminal 100 receives a notification from the stock trading service providing server 300 of the time to sell or buy stocks using a web page, an app page, a program or an application related to a stock trading service using pattern analysis, or automatically In the case of trading, it may be a terminal that sells or buys stocks through the stock trading service providing server 300 or other financial platforms by a preset amount.

Here, the at least one investor terminal 100 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop. In this case, the at least one investor terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one investor terminal 100, for example, as a wireless communication device that guarantees portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) terminal, a smartphone, a smart pad, a tablet PC, etc. may include all kinds of handheld-based wireless communication devices.

The stock trading service providing server 300 may be a server that provides a stock trading service web page, an app page, a program, or an application using pattern analysis. In addition, the stock trading service providing server 300 stores at least one type of pattern, maps it with the time of sale or purchase, and extracts it if there is a stock forming a preset pattern, and at least one investor terminal 100 ), or when automatic trading is set and the investment limit or investment amount is set in the investor terminal 100, it may be a server that controls to sell or buy stocks in response thereto.

Here, the stock trading service providing server 300 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop.

At least one information providing server 400 provides stock charts, graphs, etc. to the stock trading service providing server 300 with or without using a stock trading service-related web page, app page, program or application using pattern analysis. It can be a server that Here, the at least one information providing server 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop.

2 is a block diagram for explaining a stock trading service providing server included in the system of FIG. 1, and FIG. 3 describes an embodiment in which a stock trading service using pattern analysis according to an embodiment of the present invention is implemented. It is a drawing for

Referring to FIG. 2 , the stock trading service providing server 300 may include a setting unit 310 , a mapping unit 320 , and a trading unit 330 .

The stock trading service providing server 300 according to an embodiment of the present invention or another server (not shown) operating in conjunction with at least one investor terminal 100 and at least one information providing server 400 performs pattern analysis. When transmitting a stock trading service application, program, app page, web page, etc. used, at least one investor terminal 100 and at least one information providing server 400, a stock trading service application using a pattern analysis, a program, You can install or open app pages, web pages, and more. In addition, a service program may be driven in at least one investor terminal 100 and at least one information providing server 400 by using a script executed in a web browser. Here, the web browser is a program that enables the use of a web (WWW: World Wide Web) service, and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Netscape. , Explorer, Chrome, and the like. In addition, the application means an application on the terminal, for example, includes an app (App) executed in a mobile terminal (smartphone).

Referring to FIG. 2 , the setting unit 310 may define and store the graph shape in the stock comprehensive chart as at least one type of pattern. At this time, the F zone pattern among at least one type of pattern is formed when the condition of a stock that has surged by more than a preset 1% on the day or a stock that has reached the upper limit of the previous day is met, and then falls by more than 2% from the mid-day high of the day It may be a zone to be used and may be as shown in FIG. 3 . Here, the first percent is 17 percent and the second percent is 8 percent, and the stock price rebounds when the stock price approaches or comes into contact with the F zone. You can define F-zone trading to do so. Here, the first to fifth percent does not mean 1% to 5%, but is defined as a compound word using a prefix (first to fifth) indicating the type of percentage.

It can be defined as generating profits if the F zone is divided into three and divided into B1, B2 and B3 zones, and if the B1, B2 and B3 zones do not deviate downward. At this time, in the Z-zone pattern among at least one type of pattern, when the stock price of the stock for which a profit is generated falls again, the F zone is re-formed, and when the shunt of the stock price touches the F zone, the stock price tends to rise again may be a zone in which .

Here, after the stock price falls by more than a preset 3% from the intraday high, the F zone is touched and the rebound is F zone, the zone that rises after touching the F zone and rises and falls again is set as the K zone, the F zone and the K zone The rebound probability of can be set to be the same. Also, the third percentage may be 8%. At this time, the time when the stock price falls and touches or stays in the F zone and the K zone may be set as a buying time.

Here, the fluctuation range within B1 and B2 is detected from 11 am to 11 am from the start of the stock market, and the fluctuation range is detected from 11 am to B2 and B2 until the market close, and the graph shape of the stock touches the F and K zones. If the share price of the stock moves upward, but touches the F zone or K zone and does not ascend upward, but descends downward, you can stop loss at the preset 4th percent. In this case, the fourth percentage may be 2 to 3 percent.

<zone F>

Zone F can be created and used in many stocks, but it can shine especially in stocks that surged more than 17% on the same day and stocks that reached their high the previous day. When the above conditions are met and the stock price falls by 8% or more from the intraday high, the F zone is formed and the stock price rebounds when the stock price approaches or contacts the F zone. In one embodiment of the present invention, this trading is defined as F zone trading do. Referring to FIG. 3 , it is a case verified by the equitable movement of the stock price of Ohsung Advanced Materials on November 2, 2020, and it can be seen that the F zone is alive rather than standardized. Occasionally, it occurs according to the fluctuation of the stock price, does not occur when the conditions are not met, and after creation, it moves along with the stock price or disappears. An F zone is formed when the stock falls by more than 8% from the intraday high. Zone F is always formed, but for higher probability trading, there is a high probability when it rises by more than 17% during the day and falls by more than 8% from the high.

<K Zone>

If zone F is divided into 3 equal parts, B1, B2, and B3, if each zone does not go downward, profits rise by more than 4% and profits are generated. When the bonbon is touched, the stock price shows a trend to rise again. The zone at this time is defined as the K zone. The rebound after touching the F zone after falling more than 8% from the intraday high is called the F zone, and the zone that is created after touching the F zone and rising and falling again is called the K zone. The K-zone also has a high probability of rebounding like the F-zone, and the point to buy is when the stock price falls and touches or stays in the F-zone.

<Application time and scope>

In the morning market (until 11 am), the range of fluctuations within B1 and B2 is detected, and the range of fluctuations from B2 and B3 is detected from thereafter to the close of the market. In the case of a downward slope, in principle, a stop loss is made at 2-3%.

4A and 4B, the SF Zone pattern among at least one type of pattern is a zone formed by items that surged by more than a preset 5% on the day, and the 5th percent is 27%, When out of the SF zone, it can be set to stop loss if it is minus 2-3 percent of the stock price formed in the SF zone.

<SF Zone>

In the SF zone, items that soared by more than 27% on the day form a certain zone, which is called the SF zone. Referring to FIGS. 4A and 4B , it is a section formed in light blue. The SF zone is formed only when the above conditions are satisfied. Even if the stock price that has risen in this way falls again, there are many cases where it reaches the upper limit if it does not leave the SF zone. In principle, a -2~3% stop loss is used when it goes out of the SF zone. Catch up with the upper limit, you can get the same day profit and the next day profit, the application requirement will be the blacksmith. 2 If you are older, your chances may be slightly lower. Figure 4a is a case verified by the shunt movement of the stock price of Hyungji I&C on November 2, 2020, and Figure 4b is a case verified by the shunt movement of the stock price of Boxcell Bio on October 30, 2020.

After the stock surged by more than 27% on the same day, the SF zone was created and the stock price went up and down in the SF zone. Accordingly, the SF zone moved along with the stock price, and the stock price did not leave the SF zone and eventually reached the upper limit. Any point when the stock price falls and touches the SF zone is a buying point.

The mapping unit 320 may map and store a selling or buying time in response to at least one type of pattern. The investor terminal 100 receives a sell or buy time in response to at least one preset pattern, or sells or buys an amount of stocks corresponding to a preset amount at the time of selling or buying when automatic trading is set. can

The trading unit 330 transmits the time of purchase or purchase to the investor terminal 100, or sells an amount of stocks corresponding to the amount set in advance by the investor terminal 100 at the time of sale or purchase when automatic trading is set. Or you can buy it. At this time, since stocks are determined by various variables, they have the characteristics of non-stationarity and non-linearity. Therefore, existing analysis methodologies such as traditional statistical models did not reflect such non-normality and non-linearity, so they did not perform well in the stock trading problem. When applied as SVM, good returns were recorded or results were not at all, and in the case of the decision tree, it was not able to capture the patterns of stocks that were on the uptrend and the downtrend. Deep learning is being used in various fields and showing good results. Also, because it captures the characteristics of stocks well, the results of using it for stock trading were good. In recent studies, many studies on stock trading based on reinforcement learning have been conducted, and since good results have been obtained, in an embodiment of the present invention, stock trading can be configured to be performed by reinforcement learning.

When analyzing stocks, the most frequently used is the trend of stocks, and there are many indicators related to stock patterns to find stock patterns. . Accordingly, stocks with various trends, but largely falling, sideways, and rising, are selected one by one, and after analyzing the results by applying the Policy Gradient and ActorCritic models to each stock, a high-accuracy model By applying the above-described pattern, it is possible to construct a model for automatic trading.

Reinforcement learning is a learning method in which the agent learns the optimal behavior while interacting with the environment in a defined state. A reward according to the behavior is given to make a better behavior, and the Policy Gradient technique and the Actor Critic technique can be used.

<Policy Gradient>

Policy Gradient (PG) is a widely used reinforcement learning algorithm. This algorithm adjusts the parameter θ in the direction ∇ _θ J(π _θ ) where the objective function is differentiated with respect to θ.

The state distribution ρ ^π (s) depends on the parameters of the policy, but the policy gradient does not depend on the slope of the state distribution. This methodology has significant value because it reduces the calculation of the Performance Gradient to a simple Expectation. The problem to be solved by this algorithm is estimating the action-value function Q ^π (s,a), but it is solved by estimating the value as Q ^π (s _t ,a _t ) using Sample Return r.

<Actor-Critic>

Two key elements in PG are Policy and Action-valuefunction. In Policy Gradient, only policy is learned, but if value-function is learned, better policy can be obtained, and the algorithm that performed this is Actor-Critic. Actor-Critic consists of two models, Actor and Critic. When the action-value-function used in the algorithm is Qw(a|s), Critic updates the parameter w. Also, when the current policy is π _θ (a|s), the actor updates the parameter θ to determine the policy in the direction suggested by Critic. In other words, it can be said that Critic estimates Q-function and Actor estimates Policy.

<DMI>

In an uptrend, the high of the day will be higher than the high of the previous day, and in a downtrend, the low of the day will be lower than the low of the previous day. In order to know this trend, +DM and -DM values are calculated by comparing the high price and the low price through the following formula. In this case, +DM is the value obtained by subtracting the high price of the previous day from the high price of the day, and -DM is the value obtained by subtracting the low price of the previous day from the low price of the previous day. And in order to find out how much price change has occurred, TR (True Range) is to select the one with the largest price change among the following three cases. Here, TR is max (high price on the day - low on the day, high on the day - close on the previous day, low on the day - close on the previous day).

+DI means a line that measures whether an uptrend can be sustained within a price change, and -DI means a line where a downtrend can be sustained within a price change. Moving averages are usually 6-day or 14-day moving averages. +DI is the value obtained by dividing the moving average of +DM by the moving average of TR, and -DI is the value obtained by dividing the moving average of -DM by the moving average of TR. When the +DI and -DI lines are drawn, if the +DI line is above the -DI line, it indicates an uptrend, and if the -DI line is above the +DI line, it indicates a downtrend.

<Portfolio Value>

PV refers to the amount of cash you can get if you sell all your current stocks. If this value is greater than the initial value, it is interpreted as a gain. In this case, PV is the number of shares held multiplied by the stock price on the day and then the sum of the cash balance.

In the reinforcement learning model used in an embodiment of the present invention, the environment is stock data, the agent is the policy gradient model, the actor-critic model, the state is the stock-related index and the agent, the actions are sell, buy and hold, and the reward is higher than the threshold Gain or loss, Policy is a network that performs actions, and Critic is a network that evaluates actors.

State can be used as a state corresponding to the ratio indicator, which shows the trend through the open price, high, close, low, and trading volume data of the stock, the stock holding ratio, and the portfolio value ratio that shows the status of the agent. The actions performed by the Agent are Buy (BUY), Sell (SELL), and Hold (HOLD). A reward is not given to every action of the model, but a reward is given when a certain profit (loss) is achieved. If the return of the set threshold is exceeded, the ratio of the increased portfolio can be given, and in case of a loss, compensation can be given as much as the ratio of the portfolio that has fallen.

PG's Network can be configured by stacking LSTMs in three layers, and the last layer can use a Dense layer whose output dimension is the number of actions for outputting Actions. Finally, we can use the softmax function to make the probability of performing an action. Learning-rate can be set and adjusted. AC network has Actor Network and Critic Network, respectively, and in the case of Actor, it can be configured in the same way as Policy Gradient Policy. Critic can use 1 LSTM and a Dense layer with an output dimension of 1. Finally, a value-function value must be obtained, so a linear function can be used. Both PG and AC optimizers are Adam, and the dropout value can also be adjusted.

In order to train the two reinforcement learning models, using the DMI index to select a declining stock, a sideways stock, and a rising stock, collect data for a preset period, for example, 2 years, and the test period is the following year. It can be set to 1 year. Modeling can be started by setting each reward threshold value for learning.

Overall, PG can show better performance than AC. PG has Monte-Carlo characteristics, so you can find a section where you can make a profit even in a downtrend, but in the case of AC, it has TD (Time Difference) characteristics. This is because it may not be possible to capture profit points by updating mainly with fraudulent compensation. Even stocks that are sideways may perform poorly in both PG and AC. Policies may not converge well as positive and negative rewards continue to intersect. However, in the case of an ascending stock, both PG and AC may yield high returns, and there may be a tendency to make good policies when the reinforcement learning algorithm is ascending.

The matters that are not described with respect to the method of providing a stock trading service using the pattern analysis of FIGS. 2 and 3 are the same as those described for the method of providing a stock trading service using the pattern analysis through FIG. 1 or from the contents described above. Since it can be easily inferred, the following description will be omitted.

5 is a diagram illustrating a process in which data is transmitted/received between components included in the stock trading service providing system using the pattern analysis of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of a process in which data is transmitted/received between each component will be described with reference to FIG. 5, but the present application is not limited to such an embodiment, and the example shown in FIG. 5 according to the various embodiments described above will be described. It is apparent to those skilled in the art that the data transmission/reception process may be changed.

Referring to FIG. 5 , the stock trading service providing server defines and stores the graph shape in the stock comprehensive chart as at least one type of pattern ( S5100 ).

And, the stock trading service providing server maps and stores the selling or buying time in response to at least one type of pattern (S5200), and transmits the purchase or purchase time to the investor terminal, or sells or At the time of purchase, the investor terminal sells or buys a quantity of stocks corresponding to a preset amount (S5300).

The order between the above-described steps (S5100 to S5300) is merely an example, and is not limited thereto. That is, the order between the above-described steps ( S5100 to S5300 ) may be mutually changed, and some of these steps may be simultaneously executed or deleted.

Matters that have not been described with respect to the method of providing stock trading service using pattern analysis of FIG. 5 are the same as those described for the method of providing stock trading service using pattern analysis through FIGS. 1 to 4 or from the contents described above. Since it can be easily inferred, the following description will be omitted.

The method of providing a stock trading service using pattern analysis according to an embodiment described with reference to FIG. 5 may also be implemented in the form of a recording medium including instructions executable by a computer, such as an application or program module executed by a computer. can Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer-readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The method of providing a stock trading service using pattern analysis according to an embodiment of the present invention described above is performed by an application basically installed in a terminal (which may include a program included in a platform or operating system, etc. that is basically installed in the terminal) may be executed, and may be executed by an application (ie, a program) directly installed in the master terminal by a user through an application providing server such as an application store server, an application, or a web server related to the corresponding service. In this sense, the method for providing a stock trading service using pattern analysis according to an embodiment of the present invention described above is implemented as an application (ie, program) installed by default in a terminal or directly installed by a user, and is transmitted to a computer such as a terminal. It may be recorded on a readable recording medium.

The foregoing description of the present invention is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and likewise components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

Claims (10)

an investor terminal that receives a sell or buy time in response to at least one preset pattern, or sells or buys stocks in an amount corresponding to a preset amount at the time of selling or buying, when automatic trading is set; and
A setting unit that defines and stores the graph shape in the stock comprehensive chart as at least one type of pattern, a mapping unit that maps and stores the time of sale or purchase in response to the at least one type of pattern, the purchase or a stock trading service providing server including a trading unit that transmits a purchase time, or sells or buys an amount of stocks corresponding to the amount set in the investor terminal at the time of sale or purchase when the automatic trading is set;
Stock trading service providing system using pattern analysis, including.
The method of claim 1,
Among the at least one type of pattern, the F zone pattern is,
Stock trading service using pattern analysis, characterized in that it is a zone formed when stocks that have risen by more than 1 percent on the day or stocks that have reached the upper limit of the previous day are met and then fall by more than 2 percent from the mid-day high of the day delivery system.
3. The method of claim 2,
the first percent is 17 percent and the second percent is 8 percent;
Pattern analysis characterized in that the F zone trading is defined to be set as the selling or buying time when approaching or contacting the F zone using the fact that the stock price rebounds when the share price of the stock approaches or contacts the F zone stock trading service providing system using
3. The method of claim 2,
The F zone is divided into three and divided into B1, B2 and B3 zones, and defined as generating revenue if the B1, B2 and B3 zones do not deviate downward,
Among the at least one type of pattern, the Z zone pattern,
Pattern analysis, characterized in that the F zone is re-formed when the stock price of the stock in which the profit is generated falls again, and when the share price of the stock touches the F zone, it is a zone in which the stock price rises again is formed. stock trading service providing system using
5. The method of claim 4,
After a drop of 3% or more from the intra-day high of the stock price, the rebound after touching the F zone is the F zone,
The zone created after touching the F zone and rising and falling again is set as the K zone,
The stock trading service providing system using pattern analysis, characterized in that the rebound probability of the F zone and the K zone is set to be the same.
6. The method of claim 5,
The third percent is a stock trading service providing system using a pattern analysis, characterized in that 8%.
5. The method of claim 4,
A stock trading service providing system using pattern analysis, characterized in that the stock price falls and the point of touching or staying in the F zone and the K zone is set as a buying point.
5. The method of claim 4,
From the start of the stock market until 11 am, the range of fluctuations in B1 and B2 is detected,
From 11 am to the end of the rainy season, the range of fluctuations from B2 and B2 is sensed,
If the graph shape of the stock touches or stays in the F zone and K zone, and the stock price of the stock moves upward, but touches the F zone or K zone and does not ascend to the right, but goes downward, stop loss at the preset 4th percent A stock trading service providing system using pattern analysis, characterized in that.
9. The method of claim 8,
The fourth percent is a stock trading service providing system using a pattern analysis, characterized in that 2 to 3 percent.
The method of claim 1,
Among the at least one type of pattern, the SF Zone pattern,
It is a zone formed by stocks that have surged by more than a preset 5% on the day,
the fifth percent is 27%;
When out of the SF zone, the stock trading service providing system using pattern analysis, characterized in that the stop-loss is performed in the case of minus 2 to 3 percent of the stock price formed in the SF zone.

Images